Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add rkawaishi/workato-dev-kit --skill auto-learngit clone --depth 1 https://github.com/rkawaishi/workato-dev-kitWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/rkawaishi/workato-dev-kit/auto-learn)<a href="https://agentmods.dev/skills/rkawaishi/workato-dev-kit/auto-learn"><img src="https://agentmods.dev/badge/skills/rkawaishi/workato-dev-kit/auto-learn/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/rkawaishi/workato-dev-kit/auto-learn"><img src="https://agentmods.dev/badge/skills/rkawaishi/workato-dev-kit/auto-learn.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00074 | $0.05347 |
| Opus 5.5 | $0.00030 | $0.02139 |
| Sonnet 5.5 | $0.00015 | $0.01069 |
| Haiku 4.5 | $0.00007 | $0.00535 |
Grade A, and why
auto-learn scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 395 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/auto-learn
Drive the Workato UI through Claude in Chrome and actively collect input / output fields for every operation (trigger / action) of the target connector, then append the results to docs/connectors/<provider>.md.
Prerequisites
- Editor: Claude Code only (Cursor / Codex CLI / Gemini CLI cannot run this — they have no Chrome MCP).
- Extension: Claude in Chrome must be installed and connected. Without a connection, calls like
tabs_context_mcpornavigatewill fail (check connection state withmcp__Claude_in_Chrome__list_connected_browsers). - Workato login: a tab signed in to the target workspace UI must exist (the skill does not log in for you).
Design principles (important)
This skill is designed for autonomy first, breadth second. The goal is to spread some level of field coverage across many connectors, not to nail every type or nesting structure perfectly. Fine-grained corrections come later from manual recipes or /learn-recipe.
- No interaction: a single invocation tries every op of the target connector. Do not ask the user mid-run. With no basis for a decision, defaults → skip + log.
- Fail-soft: wrap each op in try / catch and keep going on failure. One op's failure does not abort the run.
- Record-driven: append what you got, mark what you didn't as "learning failure / partial learning". Report at the end.
- UI only: no new fetch / XHR against internal APIs (reverse engineering is strictly forbidden). Only passive observation of responses triggered by UI actions is allowed. See
@docs/patterns/auto-learn-ui-operations.md.
Usage
/auto-learn <provider>
Options:
--recipe-id <id>— recipe ID used for verification (default: inferred from the conventional recipe name or from the previous tab's URL).--workspace-url <url>— workspace base URL (default: previous tab).--force— relearn even if field details already exist in docs.--triggers-only/--actions-only— narrow the scope.--sandbox <json>— test data for dynamic schemas (see below).--followups— no-UI mode. Aggregate the## Learning summarysections of existingdocs/connectors/*.mdand print to stdout. A<provider>argument restricts to one connector; otherwise aggregates across all 7+ connectors. The execution flow (Phases 1–5) does not run. See "Followups mode" at the end of this file.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 395 lines · 74 tokens per session scan A 90b2d22c824c
auto-learn is a skill published in the GitHub repository rkawaishi/workato-dev-kit (5 stars, last pushed 1mo ago), licensed MIT. It adds 74 tokens to every session and 5,347 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
interactive-login
Log a CLI in with a browser/device-code flow (aws sso, gh, glab, gcloud, …) and save the result to the keychain so later commands can request it through execute.credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
azure-messaging-webpubsub-java
Build real-time web applications with Azure Web PubSub SDK for Java. Use when implementing WebSocket-based messaging, live updates, chat applications, or server-to-client push notifications.
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
open-design-browser
Inspect and exercise local HTML design artifacts and library prototype previews with the existing agent-browser CLI, including screenshots, interaction checks, and rendered DOM snapshots. Use when rendered evidence helps author or review a design; excludes browser installation, remote services, and unrelated browser…